Software Engineer

Engineer – AI Systems, Infrastructure & Autonomous Intelligence Building the infrastructure powering the next generation of intelligent systems by designing scalable AI platforms, autonomous agents, and production-grade backend architectures.

Key Responsibilities

• Design and develop autonomous AI systems capable of reasoning, planning, and executing complex workflows.
• Build and optimize multi-agent architectures, persistent memory systems, retrieval pipelines (RAG), and long-context intelligence frameworks.
• Develop scalable backend services, APIs, orchestration layers, and distributed systems to support AI-native applications.
• Engineer high-performance inference infrastructure for deploying and serving large language models using modern open-source ecosystems.
• Build robust data pipelines, experimentation frameworks, evaluation workflows, and MLOps tooling for reliable model development and deployment.
• Design observability, monitoring, and reliability systems to ensure performance, scalability, and operational excellence.
• Rapidly prototype AI solutions, validate emerging technologies, and translate research into production-ready capabilities.
• Collaborate across engineering and research teams to build modular, extensible, and maintainable AI infrastructure.

Areas of Focus

• Autonomous AI Agents & Multi-Agent Systems
• Persistent Memory Architectures
• Retrieval-Augmented Generation (RAG)
• AI Orchestration & Workflow Automation
• Distributed Backend Systems
• Scalable APIs & Microservices
• ML Infrastructure & MLOps
• GPU Inference & Model Serving
• Vector Databases & Knowledge Retrieval
• AI Platform Engineering
• Observability & Reliability Engineering
• Applied AI Research & Rapid Prototyping

Technologies Python • FastAPI • Docker • PostgreSQL • Redis • Vector Databases • LangGraph • LangChain • LlamaIndex • Hugging Face • OpenAI APIs • Anthropic APIs • vLLM • Ollama • Async Processing • Distributed Systems • CI/CD • GPU Infrastructure

What This Role Is About This role sits at the intersection of software engineering, distributed systems, machine learning infrastructure, and applied AI research. It involves building foundational technologies that enable autonomous intelligence from persistent memory and collaborative agent systems to scalable inference infrastructure and production-ready AI platforms. The focus is on solving complex engineering challenges, experimenting with cutting-edge AI technologies, and delivering systems that are reliable, scalable, and designed for real-world impact.